{"as_of":"2026-08-15T19:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c4084f6a67ecc85cc4bdc3d13f1b9de6e0309e438562b2e34b3817fcd48247c9","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:57:42.821519Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.20553/citation-record","integrity":"/paper/2505.20553/integrity","json":"/paper/2505.20553/citation-record.json","paper":"/paper/2505.20553"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:45.666022Z","title":"Why bigger is not always better: on finite and infinite neural networks","venue":null,"work_id":"3943cea9-4456-4715-bff1-a4af50030eec","year":null},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.163550Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:1ee6ae222ed5e2f698ca4388ee0e4eccb08e47942920a8dbc176f0caa6fe2464","observation_id":"24ff2c9b-4e4b-4e75-b2f0-235ee3b09baa","resolution":{"observed_at":"2026-08-07T13:57:45.681790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:45.538933Z","title":"Arora, S","venue":null,"work_id":"c6fdaf84-a0d8-4d1d-9804-623077569a95","year":2018},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.266661Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:39f7aa01be1165424e82c9b6871261d20e70f9052a939a55b3154d8116410801","observation_id":"bbea2125-384a-49d4-adde-81d5c6e159dd","resolution":{"observed_at":"2026-08-07T13:57:45.571933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:45.457557Z","title":"Arora, S","venue":null,"work_id":"476cd626-814a-4aec-ad04-a55b075727b3","year":2019},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.315139Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:125e3b532a55e02657b1e2f234cb883a8675e247854e0a1e3193c4a48530ec54","observation_id":"8b7fe50e-6ee7-4b1e-9c47-121ff2c5b3eb","resolution":{"observed_at":"2026-08-07T13:57:45.484215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:45.411349Z","title":"Neural tangent kernel at initialization: linear width suffices","venue":null,"work_id":"f8b27399-1608-4dcb-ba8c-5179e02a1b2c","year":2023},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.391733Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:1e20029a2f2aae354e9fcc3e23e14e2dbd8ea51d5972400decf5fd494035a5fd","observation_id":"449185db-ac7c-4eb3-a641-7ac844677583","resolution":{"observed_at":"2026-08-07T13:57:45.432092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:41.454828Z","title":"Towards understanding the spectral bias of deep learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.454828Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:875fdb5f9aa1e73d0091bd4ce7c0abbc565cbdd993a5feea6f9396a6fd2f843f","observation_id":"7737afdf-6f53-4986-9e09-9091802e759d","resolution":{"observed_at":"2026-08-07T13:57:41.454828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03385","last_updated":"2023-04-06T21:34:13Z","snapshot_observed_at":"2026-08-13T12:07:43.496512Z","submitted_at":"2023-04-06T21:34:13Z","title":"Wide neural networks: From non-gaussian random fields at initialization to the NTK geometry of training","version":1},"cited_work":{"arxiv_id":"2304.03385","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.03385","snapshot_observed_at":"2026-08-07T13:57:43.510524Z","title":"Wide neural networks: From non-gaussian random fields at initialization to the NTK geometry of training","venue":"cs.LG","work_id":"a3921c57-cf1a-4050-8159-d3df4b425f77","year":2023},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.505309Z"},"links":{"cited_paper":"/paper/2304.03385","citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:34aa7166ec72653aba921a04af8262971b8a5ae363ccf2a2582319bed7c376a5","observation_id":"46916288-ba21-4ea6-bd94-19ed3c2882ac","resolution":{"observed_at":"2026-08-07T13:57:43.538497Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:45.334620Z","title":"Jena climate dataset","venue":null,"work_id":"560f0725-856a-4f34-a8c2-fe635d538710","year":null},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.544182Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:4c66fc40dddc4a32401ade244ce61f76f3abf3ccfa9610e4ac3c9ee5600a5070","observation_id":"6012550a-c592-413b-8cab-b4237c434d2b","resolution":{"observed_at":"2026-08-07T13:57:45.382361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:45.171521Z","title":"Mathematical aspects of deep learning","venue":null,"work_id":"ef42c10c-5ecb-48a1-bf31-716ae6dbe917","year":2023},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.580797Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:11c21063ccd344420eb694bf91540c4c6d37253bb03a7f7ef647009a1f431836","observation_id":"f82467e2-6b82-46e7-9900-6761fe0fbcb4","resolution":{"observed_at":"2026-08-07T13:57:45.236729Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:41.620681Z","title":"Approximation capabilities of multilayer feedforward networks","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.620681Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:ba53bca3243a3cbb4bf21bd7282542896ed8b0eb20ca868ef01e6990ad660aff","observation_id":"014fb4ab-672b-4fc3-a1a1-aaec2249db86","resolution":{"observed_at":"2026-08-07T13:57:41.620681Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:45.075073Z","title":"Jacot, G","venue":null,"work_id":"30a80579-f484-4d87-ae93-8e79625b69de","year":2018},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.628407Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:5c3dc74b0028a5d30caefab42017bb9b098ee3242496f7441927916e543bd4a6","observation_id":"d477264d-49c3-4f70-8c6e-f400510c4d18","resolution":{"observed_at":"2026-08-07T13:57:45.126749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.05075","last_updated":"2020-10-10T19:34:37Z","snapshot_observed_at":"2026-08-13T21:22:31.931373Z","submitted_at":"2020-10-10T19:34:37Z","title":"Unsupervised Neural Networks for Quantum Eigenvalue Problems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.05075","snapshot_observed_at":"2026-08-07T13:57:41.640698Z","title":"Unsupervised neural networks for quantum eigenvalue problems","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.640698Z"},"links":{"cited_paper":"/paper/2010.05075","citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:d13c4760cdb858fe6c59ee5c586a301e097148e479a36ec2cfec589d3f1f3008","observation_id":"b37e49f5-6555-4551-8d3b-6e99de032b89","resolution":{"observed_at":"2026-08-07T13:57:41.640698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.00451","last_updated":"2022-02-24T18:29:39Z","snapshot_observed_at":"2026-08-14T16:26:18.842083Z","submitted_at":"2022-02-24T18:29:39Z","title":"Physics-Informed Neural Networks for Quantum Eigenvalue Problems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.00451","snapshot_observed_at":"2026-08-07T13:57:41.653305Z","title":"Physics-informed neural networks for quantum eigenvalue problems","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.653305Z"},"links":{"cited_paper":"/paper/2203.00451","citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:1315b94b46f767910c303207fcfbe4162bb0ac5b634c195a003345c665546ff0","observation_id":"a7c4f79e-ff0c-4829-ac3f-9b79ffa3b5d6","resolution":{"observed_at":"2026-08-07T13:57:41.653305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:44.928171Z","title":"Generalization ability of wide neural networks on R","venue":null,"work_id":"c6ea5c98-45bb-4a3b-afbe-e393505a461a","year":null},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.675048Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:01695e649d02a232be09ce6b20470e1957c3f3245e2d6ecb22f93e42c6ba0913","observation_id":"f97ab870-ac03-4a9d-8adb-aa05cc07d561","resolution":{"observed_at":"2026-08-07T13:57:44.998039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:44.778766Z","title":null,"venue":null,"work_id":"5ef1915a-dfd4-44d5-b14f-6eab8d319a2d","year":2018},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.736115Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:fe013a8e78d4321d9886feb1696a001f672e2e592cf68ca467fb104866538c6d","observation_id":"67c89f51-05fc-4dbd-94d6-7974eec76ecc","resolution":{"observed_at":"2026-08-07T13:57:44.859141Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:44.680343Z","title":"Schoenholz, Jeffrey Pennington, Ben Adlam, Lechao Xiao, Roman Novak, and Jascha Sohl-Dickstein","venue":null,"work_id":"78e9ad82-ed6f-4e4d-a02d-880ca34a93c4","year":2020},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.763078Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:66c396114661bd6caf337f5098e7bec28c1bbebeaaa3ae685d9eadfd6bc9360f","observation_id":"3f68e172-3596-42df-a7ee-675bbd92a42e","resolution":{"observed_at":"2026-08-07T13:57:44.723390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:41.795555Z","title":"Lin, Allan Pinkus, and Shimon Schocken","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.795555Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:068f3dfc26c73689c9528a2c0d84707270dd41a80c99a248590f9e1a606fc27f","observation_id":"dd096a38-4fb7-4db6-bb74-4d53a251f60e","resolution":{"observed_at":"2026-08-07T13:57:41.795555Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:44.547046Z","title":"Statistical optimality of deep wide neural networks","venue":null,"work_id":"e747626a-0ee0-43f4-8a26-593f26631b4a","year":null},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.832513Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:4ba9dfa5e7f6d540ecc3733a82a64ed371728754f6f02d04e2d931818d1018ed","observation_id":"a2147cd3-5d77-4738-9c8b-9a8ee631710e","resolution":{"observed_at":"2026-08-07T13:57:44.599000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.19756","last_updated":"2025-02-09T21:09:09Z","snapshot_observed_at":"2026-08-15T02:33:31.807561Z","submitted_at":"2024-04-30T17:58:29Z","title":"KAN: Kolmogorov-Arnold Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.19756","snapshot_observed_at":"2026-08-07T13:57:41.945208Z","title":"Kan: Kolmogorov-arnold networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.945208Z"},"links":{"cited_paper":"/paper/2404.19756","citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:addfae1154e08e8e82d04563b5a3fd53d1f3d74fc27e7a16eaf370d8c79f432c","observation_id":"2bb43f8f-bbc9-4a14-85f4-e40eba91cfdb","resolution":{"observed_at":"2026-08-07T13:57:41.945208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.4208/cicp.oa-2020-0179","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":"Multi-scale deep neural network (mscalednn) for solving poisson-boltzmann equation in complex domains","venue":"Communications in Computational Physics","work_id":"2d36c883-81cd-49b9-9ba8-ab6b5b0c029f","year":1970},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.007314Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:e00d69fc86a8c9a2275767f2067056a50c5fc185eb06184d94130c172a00e88f","observation_id":"0af213b2-f87e-4cdc-8baf-998033f198c1","resolution":{"observed_at":"2026-08-07T13:57:42.942807Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.02657","last_updated":"2026-04-07T08:34:57Z","snapshot_observed_at":"2026-08-02T17:41:19.503879Z","submitted_at":"2023-05-04T08:54:40Z","title":"On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.02657","snapshot_observed_at":"2026-08-07T13:57:41.872473Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.872473Z"},"links":{"cited_paper":"/paper/2305.02657","citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:27b71e3d6f11ea2a177b35283a5ca582e58871f3e9643e747aa6fded5e161f3c","observation_id":"6e59a18e-70ca-49cb-bcea-a2ddfdb37f0f","resolution":{"observed_at":"2026-08-07T13:57:41.872473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:44.303330Z","title":null,"venue":null,"work_id":"e4c4f0a4-a220-4ef7-a7cc-628221062fb9","year":1994},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.128581Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:d9f2f83bfba2c46d202c74bf25b4f42187c3a42e8eca0cf93befd052efb4868c","observation_id":"59e23fe7-637d-4174-af4d-28c0f47be6a0","resolution":{"observed_at":"2026-08-07T13:57:44.360314Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:44.174037Z","title":"On the spectral bias of neural networks","venue":null,"work_id":"0a952514-7728-48a5-9778-830bad5726fc","year":null},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.180827Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:864328406909615181c615dfdcac329761eb61503974ed6b2682c7e8a411fa1e","observation_id":"424d6467-4f2c-4a5c-ba12-2fac5d17d3a7","resolution":{"observed_at":"2026-08-07T13:57:44.208100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:44.424712Z","title":"The limitations of large width in neural networks: A deep gaussian process perspective","venue":null,"work_id":"1a1e1324-ee60-49b0-b8d6-81eaa824e23f","year":2021},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.074081Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:cce42a129bfc5edcf19101a6d86cc9efe87431ce175d6ac4b0650c1c6842da59","observation_id":"d6402c6d-b7f4-4711-a39f-f18ca3e564bd","resolution":{"observed_at":"2026-08-07T13:57:44.469150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:43.875263Z","title":"Martel, Alexander W","venue":null,"work_id":"a8234b19-87d9-4f56-aa26-7a5bb58589cd","year":2020},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.387722Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:ddb505166dd4305bb56fd4961642d85a77c20120df692a76457e76430a918a75","observation_id":"4dbf21d4-cd6a-49c4-a885-a0d51ae568b7","resolution":{"observed_at":"2026-08-07T13:57:43.938054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:43.753932Z","title":"fourier-feature-networks","venue":null,"work_id":"0f4478b4-4b14-4c66-b859-19a58c4c2dd5","year":null},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.460277Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:ad937630d1a8b64f87c43590d82095b0c9bbc0e9b76b30cf494add53af1e6532","observation_id":"0da6d759-4c58-40f1-9961-02eaddd04cf0","resolution":{"observed_at":"2026-08-07T13:57:43.795111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:44.003884Z","title":null,"venue":null,"work_id":"e5ac1af7-f3c4-44fc-9fa6-411a8e70d781","year":2022},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.279662Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:8886aafd8b27a4191a18a31c1916f47f091cef8087c6b4eb83bf1dc1596fd6cf","observation_id":"4a50c8fe-85ca-4bba-becc-34b3e766de29","resolution":{"observed_at":"2026-08-07T13:57:44.089531Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:42.557997Z","title":"On the eigenvector bias of fourier feature net- works: From regression to solving multi-scale pdes with physics-informed neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.557997Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:92a22911d3127a6592077c1e66cce5fc4b81a2cc2305ef35c88d13133569bf25","observation_id":"9d6a6772-cdbb-42bf-aa0e-061bbce7cca3","resolution":{"observed_at":"2026-08-07T13:57:42.557997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:42.512995Z","title":"Fourier features let networks learn high frequency functions in low dimensional domains","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.512995Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:e463c1ba347aba518cfa9403cae0bd3cce9408a86cabbd297d6c246d997c023d","observation_id":"41335b8f-584e-467f-ac71-528bd2e812ab","resolution":{"observed_at":"2026-08-07T13:57:42.512995Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.04760","last_updated":"2020-04-04T22:53:19Z","snapshot_observed_at":"2026-08-14T17:17:07.234917Z","submitted_at":"2019-02-13T06:09:18Z","title":"Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.04760","snapshot_observed_at":"2026-08-07T13:57:42.783867Z","title":"Scaling limits of wide neural networks with weight sharing: Gaussian process behavior, gradient independence, and neural tangent kernel derivation","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.783867Z"},"links":{"cited_paper":"/paper/1902.04760","citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:9b03c0197d13b9e67808e809cb27aad947ff5b908f5840da52a00ad4a26a3410","observation_id":"cfb6856f-6604-481a-8abb-1ba2473e29a7","resolution":{"observed_at":"2026-08-07T13:57:42.783867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.09184","last_updated":"2022-11-28T16:57:52Z","snapshot_observed_at":"2026-08-13T13:40:49.970955Z","submitted_at":"2022-11-16T20:07:55Z","title":"An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.09184","snapshot_observed_at":"2026-08-07T13:57:42.821519Z","title":"1 2Bit/jα eiBt/jα sin(xLt/jα−1) xLt/jα−1 − 1 ! + 1 2 # × NY j=⌈B/xL⌉","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.821519Z"},"links":{"cited_paper":"/paper/2211.09184","citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:453d400cc14962d220bfcc3d7a6fe948238d69e8d5058425ac7e68462b38b4c2","observation_id":"c0a210b3-d598-4137-9a34-03e5d45ad7b5","resolution":{"observed_at":"2026-08-07T13:57:42.821519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:43.618360Z","title":"Yang and E","venue":null,"work_id":"bc0b08e8-72b7-4c33-b669-96379033d064","year":2021},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:42.741666Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:1e96c3068870b85266e1ab045885f65ee85be9b8e0e75a0c78128eb99df3e2fc","observation_id":"de43c385-8f76-459f-9082-0ad5bbd49581","resolution":{"observed_at":"2026-08-07T13:57:43.682889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:57:45.612056Z","title":null,"venue":null,"work_id":"bbc03e36-df32-439a-9a2d-b3eb7460ba45","year":null},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.205868Z"},"links":{"citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:609a0586f0cd55226246d70606e4ae36ce42b208391df02ec357851fba21b97c","observation_id":"ba2a9b05-ceeb-4398-9dbe-34f6ff41977d","resolution":{"observed_at":"2026-08-07T13:57:45.637095Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.05933","last_updated":"2023-02-12T15:07:27Z","snapshot_observed_at":"2026-08-13T12:45:58.661911Z","submitted_at":"2023-02-12T15:07:27Z","title":"Generalization Ability of Wide Neural Networks on $\\mathbb{R}$","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.05933","snapshot_observed_at":"2026-08-07T13:57:41.705012Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T13:57:41.705012Z"},"links":{"cited_paper":"/paper/2302.05933","citing_paper":"/paper/2505.20553"},"observation_digest":"sha256:4b6392442e7b83b33ecd90ca66c5260839bde1ac2a11b88b9457c1bd3ffb7a8e","observation_id":"2031aa42-4661-40d5-a54d-274f5dc7f218","resolution":{"observed_at":"2026-08-07T13:57:41.705012Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.20553","last_updated":"2025-07-31T11:11:42Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T05:59:55.469135Z","submitted_at":"2025-05-26T22:26:55Z","title":"A ZeNN architecture to avoid the Gaussian trap"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":2,"verified_fuzzy":15},"total_outbound_references":33},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2505.20553."}